agentleFS
Sign inStart free
joinwell52-AIjoinwell52-AI/CodeFlowMu-open/skills/browser-playwright-check/SKILL.md

browser-playwright-check

Skill2 starsChanged 4 months agoMITView on GitHub

Use when an agent needs to operate or verify a web page with Playwright, including screenshots, viewport checks, navigation, forms, clicks, canvas visibility, responsive layout, or local Panel/browser behavior.

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 14 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈14

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when the task requires browser-visible evidence or interactive web verification.

    line 10
  2. Distinctive:

    Verify responsive layouts across desktop and mobile viewports.

    line 17
  3. Distinctive:

    Check canvas, media, animation, or visual nonblank rendering.

    line 18
  4. Distinctive:

    Prefer an existing project test command if it already uses Playwright.

    line 23
  5. Distinctive:

    If no test exists, write the smallest ad hoc Playwright check needed for evidence.

    line 24
  6. Distinctive:

    Use stable selectors where available.

    line 25
  7. Distinctive:

    Verify behavior, not only file existence.

    line 26
  8. Distinctive:

    Keep browser automation scoped to local/dev URLs or explicit user-provided URLs.

    line 28
  9. Distinctive:

    Do not require network access unless the task explicitly depends on a remote page.

    line 29
  10. Distinctive:

    Do not hide flaky or unverified criteria in the final report.

    line 30
  11. Distinctive:

    Do not use Playwright as a substitute for code review when source inspection is required.

    line 44
  12. Distinctive:

    Do not perform destructive UI actions unless explicitly authorized.

    line 45
  13. Distinctive:

    Do not log secrets, session tokens, cookies, or private form data.

    line 46
  14. Distinctive:

    Do not mark a visual/UI task done without at least one browser-visible verification when a browser can run locally.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Browser Playwright Check

When to use

Use when the task requires browser-visible evidence or interactive web verification.

Typical triggers:

  • Open a local HTML file or dev-server URL in a browser.
  • Click through UI, fill a form, test navigation, or inspect page state.
  • Capture screenshots for evidence.
  • Verify responsive layouts across desktop and mobile viewports.
  • Check canvas, media, animation, or visual nonblank rendering.
  • Diagnose Panel or web app behavior that cannot be proven by static code reading.

Rules

  • Prefer an existing project test command if it already uses Playwright.
  • If no test exists, write the smallest ad hoc Playwright check needed for evidence.
  • Use stable selectors where available; otherwise use visible text, roles, or narrow DOM queries.
  • Verify behavior, not only file existence.
  • Capture evidence: command output, screenshot paths, viewport sizes, URL, and pass/fail notes.
  • Keep browser automation scoped to local/dev URLs or explicit user-provided URLs.
  • Do not require network access unless the task explicitly depends on a remote page.
  • Do not hide flaky or unverified criteria in the final report.

Required output

When reporting, include:

  • URL or local file opened.
  • Viewports tested.
  • Interactions performed.
  • Evidence paths for screenshots or traces when captured.
  • Any untested or flaky criteria.

Forbidden actions

  • Do not use Playwright as a substitute for code review when source inspection is required.
  • Do not perform destructive UI actions unless explicitly authorized.
  • Do not log secrets, session tokens, cookies, or private form data.
  • Do not mark a visual/UI task done without at least one browser-visible verification when a browser can run locally.

Minimal example

Check: open http://127.0.0.1:5173, click "Submit", verify success toast
Viewport: 1280x720 and 390x844
Evidence: screenshots/playwright-submit-desktop.png
Result: pass

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free